English
Related papers

Related papers: PIT: Position-Invariant Transform for Cross-FoV Do…

200 papers

Applying the knowledge of an object detector trained on a specific domain directly onto a new domain is risky, as the gap between two domains can severely degrade model's performance. Furthermore, since different instances commonly embody…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Minghao Xu , Hang Wang , Bingbing Ni , Qi Tian , Wenjun Zhang

Domain adaptation methods face performance degradation in object detection, as the complexity of tasks require more about the transferability of the model. We propose a new perspective on how CNN models gain the transferability, viewing the…

Computer Vision and Pattern Recognition · Computer Science 2021-05-11 Yu Wang , Rui Zhang , Shuo Zhang , Miao Li , YangYang Xia , XiShan Zhang , ShaoLi Liu

We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context self-attention modules, joint with standard local…

Computer Vision and Pattern Recognition · Computer Science 2023-06-07 Ali Hatamizadeh , Hongxu Yin , Greg Heinrich , Jan Kautz , Pavlo Molchanov

Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one domain to another (e.g., synthetic to real images). The adapted representations often do not capture pixel-level domain shifts that are crucial for…

Computer Vision and Pattern Recognition · Computer Science 2020-01-13 Yun-Chun Chen , Yen-Yu Lin , Ming-Hsuan Yang , Jia-Bin Huang

The rise of pre-trained language models has yielded substantial progress in the vast majority of Natural Language Processing (NLP) tasks. However, a generic approach towards the pre-training procedure can naturally be sub-optimal in some…

Computation and Language · Computer Science 2021-09-03 Entony Lekhtman , Yftah Ziser , Roi Reichart

This paper addresses domain adaptation for the pixel-wise classification of remotely sensed data using deep neural networks (DNN) as a strategy to reduce the requirements of DNN with respect to the availability of training data. We focus on…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Dennis Wittich , Franz Rottensteiner

This paper presents FogAdapt, a novel approach for domain adaptation of semantic segmentation for dense foggy scenes. Although significant research has been directed to reduce the domain shift in semantic segmentation, adaptation to scenes…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Javed Iqbal , Rehan Hafiz , Mohsen Ali

In this work, we explore the usage of the Frequency Transformation for reducing the domain shift between the source and target domain (e.g., synthetic image and real image respectively) towards solving the Domain Adaptation task. Most of…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Vikash Kumar , Himanshu Patil , Rohit Lal , Anirban Chakraborty

The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…

Machine Learning · Computer Science 2019-06-11 Yiying Li , Yongxin Yang , Wei Zhou , Timothy M. Hospedales

In this paper, we consider domain-adaptive imitation learning with visual observation, where an agent in a target domain learns to perform a task by observing expert demonstrations in a source domain. Domain adaptive imitation learning…

Machine Learning · Computer Science 2023-12-04 Sungho Choi , Seungyul Han , Woojun Kim , Jongseong Chae , Whiyoung Jung , Youngchul Sung

Vision-language models pre-trained at large scale have shown unprecedented adaptability and generalization to downstream tasks. Although its discriminative potential has been widely explored, its reliability and uncertainty are still…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Julio Silva-Rodríguez , Ismail Ben Ayed , Jose Dolz

Source-Free Domain Adaptation (SFDA) seeks to adapt a source model, which is pre-trained on a supervised source domain, for a target domain, with only access to unlabeled target training data. Relying on pseudo labeling and/or auxiliary…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Song Tang , Yunxiang Bai , Wenxin Su , Mao Ye , Jianwei Zhang , Xiatian Zhu

Despite the success of deep learning-based object detection methods in recent years, it is still challenging to make the object detector reliable in adverse weather conditions such as rain and snow. For the robust performance of object…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Minsik Jeon , Junwon Seo , Jihong Min

Typically, object detection methods for autonomous driving that rely on supervised learning make the assumption of a consistent feature distribution between the training and testing data, this such assumption may fail in different weather…

Computer Vision and Pattern Recognition · Computer Science 2024-08-22 Jinlong Li , Runsheng Xu , Xinyu Liu , Jin Ma , Baolu Li , Qin Zou , Jiaqi Ma , Hongkai Yu

This paper addresses the problem of cross-view image geo-localization, where the geographic location of a ground-level street-view query image is estimated by matching it against a large scale aerial map (e.g., a high-resolution satellite…

Computer Vision and Pattern Recognition · Computer Science 2019-11-28 Yujiao Shi , Xin Yu , Liu Liu , Tong Zhang , Hongdong Li

Domain shift is a very challenging problem for semantic segmentation. Any model can be easily trained on synthetic data, where images and labels are artificially generated, but it will perform poorly when deployed on real environments. In…

Computer Vision and Pattern Recognition · Computer Science 2020-09-03 Luigi Musto , Andrea Zinelli

We study permutation invariant training (PIT), which targets at the permutation ambiguity problem for speaker independent source separation models. We extend two state-of-the-art PIT strategies. First, we look at the two-stage speaker…

Sound · Computer Science 2021-04-06 Xiaoyu Liu , Jordi Pons

Building upon the impressive success of CLIP (Contrastive Language-Image Pretraining), recent pioneer works have proposed to adapt the powerful CLIP to video data, leading to efficient and effective video learners for open-vocabulary action…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Kun-Yu Lin , Henghui Ding , Jiaming Zhou , Yu-Ming Tang , Yi-Xing Peng , Zhilin Zhao , Chen Change Loy , Wei-Shi Zheng

This paper strives for activity recognition under domain shift, for example caused by change of scenery or camera viewpoint. The leading approaches reduce the shift in activity appearance by adversarial training and self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Yunhua Zhang , Hazel Doughty , Ling Shao , Cees G. M. Snoek

We address the task of domain adaptation in object detection, where there is a domain gap between a domain with annotations (source) and a domain of interest without annotations (target). As an effective semi-supervised learning method, the…

Computer Vision and Pattern Recognition · Computer Science 2022-05-13 Yu-Jhe Li , Xiaoliang Dai , Chih-Yao Ma , Yen-Cheng Liu , Kan Chen , Bichen Wu , Zijian He , Kris Kitani , Peter Vajda